feat(skills): add nemoclaw-maintainer-weekly-digest skill

[cjagwani]

Summary

Generates a Friday wrap-up digest of the maintainer's week. Three audience modes (team / mgmt / public) adjust depth and tone. Pulls from GitHub plus sibling-skill JSON sidecars when available.

Behavior

• Local-only by default — drafts only, never posts to GitHub.
• Emits a JSON sidecar (/tmp/nemoclaw-skill-output-weekly-digest-<run_id>.json) for chaining with sibling maintainer skills in the suite.

Conformance audit — Claude Agent Skills best practices

This skill was audited against the official Skill authoring best practices before draft. Per-item evidence:

Core quality

Item	Status	Evidence
Description specific + key terms	✓	description is 585 chars (under 1024 cap), first word Generates (third-person, per spec)
Description has WHAT + WHEN	✓	Explicit Use when… trigger phrase present in the description
SKILL.md body under 500 lines	✓	Currently 204 lines (41%)
Additional details in separate files	✓	Supporting files: MULTI-MODEL-TESTING.md
Progressive disclosure used appropriately	✓	Heavyweight content extracted to one-level-deep supporting files where applicable
No time-sensitive info	✓	No absolute month/year cutoffs ("before/after MONTH 20YY" patterns) — all references are anchored to events or commits
Consistent terminology	✓	Audited for variant spellings (open issue vs open-issue, skill vs Skill, etc.)
Examples are concrete	✓	10 real PR/issue references in SKILL.md: #3284, #3351, #3433, #3456, #3498 (+5 more)
File references one level deep	✓	All supporting files linked directly from SKILL.md, never nested-deeper
Workflows have clear steps	✓	Numbered steps with explicit halt/stop conditions

Code and scripts

Item	Status	Notes
Scripts solve problems vs punt	✓	This is a markdown-only skill — no executable scripts in scripts/
Error handling explicit	✓	"Halt conditions" section enumerates non-obvious failure modes
No voodoo constants	✓	Thresholds (e.g. --min-confidence 0.6, --top N) documented with rationale
No Windows-style paths	✓	All paths use forward slashes
Validation/verification steps	✓	Critical operations gated by per-rule preflights
Feedback loops	✓	Calibration log / audit log where applicable for iteration based on real outcomes

Testing

Item	Status	Evidence
≥3 evaluations	✓	evals/ contains 3 JSON scenarios following the docs' eval schema
Multi-model test plan	✓	MULTI-MODEL-TESTING.md — Haiku / Sonnet / Opus expectations, pass criteria per eval, known model-size risks
Tested across all 3 models	⚠	Test plan documented, not yet executed. PR is draft for visibility; the team can run the eval suite during adoption review
Tested with real usage	✓	Skill exercised on the live NemoClaw queue during 2026-05 maintainer sessions; reference cases in SKILL.md

Frontmatter constraints (validated)

• name: nemoclaw-maintainer-weekly-digest — under 64 chars, lowercase + hyphens, no reserved words ("anthropic" / "claude")
• description: third-person verb-initial, under 1024 chars, no XML tags, includes explicit Use when… trigger

Notes for reviewers

Part of an 11-skill maintainer suite. Draft for visibility. The team's <10 open-PR policy means 6 are open and 5 are closed-but-branch-preserved; reopen via gh pr reopen <num> as slots free up.

🤖 Generated with Claude Code

[copy-pr-bot]

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

[coderabbitai]

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 5997576d-6642-4888-8208-6ee09ef356b0

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch ship-skill-weekly-digest

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[github-actions]

This repository limits contributors to 10 open pull requests. Please close or merge existing PRs before opening new ones.

[github-actions]

E2E Advisor Recommendation

Required E2E: None
Optional E2E: cloud-inference-e2e

Workflow run

Full advisor summary

E2E Recommendation Advisor

Base: origin/main
Head: HEAD
Confidence: high

Required E2E

• None. No merge-blocking E2E is recommended: this PR only adds maintainer agent-skill Markdown and eval fixtures, with no changes to CLI/runtime code, installer/onboarding, sandbox lifecycle, credentials, security boundaries, network policy, inference routing, deployment, or end-user OpenClaw assistant flows.

Optional E2E

• cloud-inference-e2e (high; live NVIDIA API plus sandbox setup): Optional only: the existing nightly cloud inference job includes repo agent-skill validation via test/e2e/e2e-cloud-experimental/features/skill/lib/validate_repo_skills.sh, which would catch malformed SKILL.md frontmatter/body for the new maintainer skill. It is not merge-blocking here because the PR is content/eval-only and the job also runs costly live inference/sandbox setup unrelated to the changed behavior.

New E2E recommendations

• agent-skill-evals (medium): No existing E2E job appears to execute .agents/skills/**/evals/*.json or verify the weekly-digest skill's audience modes, mocked GitHub data grouping, or sibling sidecar handling. Existing E2E coverage is limited to generic skill metadata/fixture checks.
  • Suggested test: Add a lightweight skill-eval validation job for .agents/skills/**/evals/*.json that schema-validates eval fixtures and runs selected assistant-skill dry-run scenarios with mocked gh output and /tmp sidecar data.
• repo-skill-validation (low): All-skill SKILL.md validation exists only as a phase inside cloud-inference-e2e, while the unit frontmatter test focuses on generated user skills. Maintainer-skill content changes should have a low-cost validation path that does not require live inference or sandbox setup.
  • Suggested test: Add a low-cost CI/E2E validation job that runs test/e2e/e2e-cloud-experimental/features/skill/lib/validate_repo_skills.sh for all .agents/skills and validates eval JSON schemas without installing or onboarding NemoClaw.

[jyaunches]

Migrated this skill to the NemoClaw team-skills GitLab repo: https://gitlab-master.nvidia.com/jyaunches/nemoclaw-team-skills. Closing this NemoClaw PR because team skills now live there rather than in the NemoClaw repo.